Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to self-related actions or methods in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    test code invocation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.46
    UserScript
    -0.45
    ngdoc
    -0.43
    endregion
    -0.42
    ंदीखरीदारी
    -0.41
    comp
    -0.41
     Dag
    -0.39
    Espèce
    -0.38
     Western
    -0.38
     &___
    -0.37
    POSITIVE LOGITS
     unittest
    0.53
    MemoryWarning
    0.45
     sumpay
    0.43
    󠁢
    0.43
    webElement
    0.42
     testCase
    0.41
     oprot
    0.41
    KURZBESCHREIBUNG
    0.41
     TestCase
    0.40
     Lokales
    0.40
    Act Density 0.005%

    No Known Activations